Terjman-Large-v2 / tokenizer_config.json
BounharAbdelaziz's picture
Training in progress, step 500
debd118 verified
raw
history blame
824 Bytes
{
"added_tokens_decoder": {
"25897": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"30683": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"61246": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"clean_up_tokenization_spaces": true,
"eos_token": "</s>",
"model_max_length": 512,
"pad_token": "<pad>",
"separate_vocabs": false,
"source_lang": "en",
"sp_model_kwargs": {},
"target_lang": "ar",
"tokenizer_class": "MarianTokenizer",
"unk_token": "<unk>"
}